MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

ArXi:2605.22794v1 Announce Type: new Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine evolution to text-mutable artifacts -- skill files, prompt configurations, memory schemas, workflow graphs -- and leave the agent harness untouched.